import pandas as pd
import seaborn as sns
import plotly.express as px
import numpy as np
import matplotlib.pyplot as plt

import plotly.io as pio
pio.renderers.default = "plotly_mimetype+notebook"

Matplotlib

For this excercise, we have written the following code to load the stock dataset built into plotly express.

stocks = px.data.stocks()
stocks.head()

	date	GOOG	AAPL	AMZN	FB	NFLX	MSFT
0	2018-01-01	1.000000	1.000000	1.000000	1.000000	1.000000	1.000000
1	2018-01-08	1.018172	1.011943	1.061881	0.959968	1.053526	1.015988
2	2018-01-15	1.032008	1.019771	1.053240	0.970243	1.049860	1.020524
3	2018-01-22	1.066783	0.980057	1.140676	1.016858	1.307681	1.066561
4	2018-01-29	1.008773	0.917143	1.163374	1.018357	1.273537	1.040708

Question 1:

Select a stock and create a suitable plot for it. Make sure the plot is readable with relevant information, such as date, values.

ax = plt.axes()

ax.xaxis.set_major_locator(ticker.MultipleLocator(5))

ax.xaxis.set_minor_locator(ticker.MultipleLocator(1))

# First instantiate an Axes object - used to manage the axes in the graph: ax=plot.Axes().
# Then use the Locator instance to set the primary and secondary scales for the x-axis (ax.xaxis) or y-axis (ax.yaxis).

import matplotlib.ticker as ticker
x=stocks['date']
y=stocks['GOOG']
plt.figure(figsize=(12,9))
ax = plt.axes()
ax.xaxis.set_major_locator(ticker.MultipleLocator(12))
plt.plot(x,y)
plt.xlabel('date')
plt.ylabel('stock value')
plt.title('Google stock')
plt.show()

# YOUR CODE HERE

Question 2:

You've already plot data from one stock. It is possible to plot multiples of them to support comparison.
To highlight different lines, customise line styles, markers, colors and include a legend to the plot.

# YOUR CODE HERE
x=stocks['date']
y=stocks['GOOG']
plt.figure(figsize=(12,9))
ax = plt.axes()
ax.xaxis.set_major_locator(ticker.MultipleLocator(12))
plt.plot(x,y)
for i in list(stocks.columns)[2:]:
    plt.plot(x,stocks[i])

plt.xlabel('date')
plt.ylabel('stock value')
plt.title('Google stock')
plt.legend([x for x in list(stocks.columns)[1:]])
plt.show()

Seaborn

First, load the tips dataset

tips = sns.load_dataset('tips')
tips.head()

	total_bill	tip	sex	smoker	day	time	size
0	16.99	1.01	Female	No	Sun	Dinner	2
1	10.34	1.66	Male	No	Sun	Dinner	3
2	21.01	3.50	Male	No	Sun	Dinner	3
3	23.68	3.31	Male	No	Sun	Dinner	2
4	24.59	3.61	Female	No	Sun	Dinner	4

Question 3:

Let's explore this dataset. Pose a question and create a plot that support drawing answers for your question.

Some possible questions:

• Are there differences between male and female when it comes to giving tips?
• What attribute correlate the most with tip?

# YOUR CODE HERE
#Are there differences between male and female when it comes to giving tips?
sns.violinplot(x='day',y='tip',hue='sex',data=tips)

<AxesSubplot:xlabel='day', ylabel='tip'>

Males are found to give more tips.

#What attribute correlate the most with tip
sns.set_style("ticks")
sns.pairplot(tips,hue = 'sex',diag_kind = "kde",kind = "scatter",palette = "husl")
plt.show()

Plotly Express

Question 4:

Redo the above exercises (challenges 2 & 3) with plotly express. Create diagrams which you can interact with.

The stocks dataset

Hints:

• Turn stocks dataframe into a structure that can be picked up easily with plotly express

stocks = px.data.stocks()
stocks

	date	GOOG	AAPL	AMZN	FB	NFLX	MSFT
0	2018-01-01	1.000000	1.000000	1.000000	1.000000	1.000000	1.000000
1	2018-01-08	1.018172	1.011943	1.061881	0.959968	1.053526	1.015988
2	2018-01-15	1.032008	1.019771	1.053240	0.970243	1.049860	1.020524
3	2018-01-22	1.066783	0.980057	1.140676	1.016858	1.307681	1.066561
4	2018-01-29	1.008773	0.917143	1.163374	1.018357	1.273537	1.040708
...	...	...	...	...	...	...	...
100	2019-12-02	1.216280	1.546914	1.425061	1.075997	1.463641	1.720717
101	2019-12-09	1.222821	1.572286	1.432660	1.038855	1.421496	1.752239
102	2019-12-16	1.224418	1.596800	1.453455	1.104094	1.604362	1.784896
103	2019-12-23	1.226504	1.656000	1.521226	1.113728	1.567170	1.802472
104	2019-12-30	1.213014	1.678000	1.503360	1.098475	1.540883	1.788185

105 rows × 7 columns

new=stocks.set_index(['date'])
new=new.stack().reset_index()
new
new=new.rename(columns={'level_1':'Type',0:'Value'})
new#Now the structure of new can be used by px

	date	Type	Value
0	2018-01-01	GOOG	1.000000
1	2018-01-01	AAPL	1.000000
2	2018-01-01	AMZN	1.000000
3	2018-01-01	FB	1.000000
4	2018-01-01	NFLX	1.000000
...	...	...	...
625	2019-12-30	AAPL	1.678000
626	2019-12-30	AMZN	1.503360
627	2019-12-30	FB	1.098475
628	2019-12-30	NFLX	1.540883
629	2019-12-30	MSFT	1.788185

630 rows × 3 columns

new.head()

	date	Type	Value
0	2018-01-01	GOOG	1.0
1	2018-01-01	AAPL	1.0
2	2018-01-01	AMZN	1.0
3	2018-01-01	FB	1.0
4	2018-01-01	NFLX	1.0

# YOUR CODE HERE
# df=px.data.new()
fig=px.line(new,x='date',y='Value',color='Type',hover_name='Type')
fig.show()

The tips dataset

# YOUR CODE HERE
df=px.data.tips()
df

	total_bill	tip	sex	smoker	day	time	size
0	16.99	1.01	Female	No	Sun	Dinner	2
1	10.34	1.66	Male	No	Sun	Dinner	3
2	21.01	3.50	Male	No	Sun	Dinner	3
3	23.68	3.31	Male	No	Sun	Dinner	2
4	24.59	3.61	Female	No	Sun	Dinner	4
...	...	...	...	...	...	...	...
239	29.03	5.92	Male	No	Sat	Dinner	3
240	27.18	2.00	Female	Yes	Sat	Dinner	2
241	22.67	2.00	Male	Yes	Sat	Dinner	2
242	17.82	1.75	Male	No	Sat	Dinner	2
243	18.78	3.00	Female	No	Thur	Dinner	2

244 rows × 7 columns

fig=px.scatter(df,x='total_bill',y='tip',color='sex',facet_col='smoker',facet_row='time')
fig.show()

Question 5:

Recreate the barplot below that shows the population of different continents for the year 2007.

Hints:

• Extract the 2007 year data from the dataframe. You have to process the data accordingly
• use plotly bar
• Add different colors for different continents
• Sort the order of the continent for the visualisation. Use axis layout setting
• Add text to each bar that represents the population

#load data
df = px.data.gapminder()

import plotly.graph_objects as go
df=df[df['year']==2007]
df

	country	continent	year	lifeExp	pop	gdpPercap	iso_alpha	iso_num
11	Afghanistan	Asia	2007	43.828	31889923	974.580338	AFG	4
23	Albania	Europe	2007	76.423	3600523	5937.029526	ALB	8
35	Algeria	Africa	2007	72.301	33333216	6223.367465	DZA	12
47	Angola	Africa	2007	42.731	12420476	4797.231267	AGO	24
59	Argentina	Americas	2007	75.320	40301927	12779.379640	ARG	32
...	...	...	...	...	...	...	...	...
1655	Vietnam	Asia	2007	74.249	85262356	2441.576404	VNM	704
1667	West Bank and Gaza	Asia	2007	73.422	4018332	3025.349798	PSE	275
1679	Yemen, Rep.	Asia	2007	62.698	22211743	2280.769906	YEM	887
1691	Zambia	Africa	2007	42.384	11746035	1271.211593	ZMB	894
1703	Zimbabwe	Africa	2007	43.487	12311143	469.709298	ZWE	716

142 rows × 8 columns

a=df.loc[:,['continent','pop']]
a

	continent	pop
11	Asia	31889923
23	Europe	3600523
35	Africa	33333216
47	Africa	12420476
59	Americas	40301927
...	...	...
1655	Asia	85262356
1667	Asia	4018332
1679	Asia	22211743
1691	Africa	11746035
1703	Africa	12311143

142 rows × 2 columns

b=a.groupby('continent').sum()
c=b.reset_index()
c

	continent	pop
0	Africa	929539692
1	Americas	898871184
2	Asia	3811953827
3	Europe	586098529
4	Oceania	24549947

# #First method go.Figure
# fig=go.Figure(data=go.Bar(y=df['continent'],x=df['pop'],orientation='h',color='continent'))
# fig.show()

# YOUR CODE HERE
fig=px.bar(c,x='pop',y='continent',color='continent',text='pop')
fig.show()

fig.update_yaxes(categoryorder='total ascending')#order should be determined by the numerical order of the values

fig.update_traces(textposition='outside',selector=dict(type='bar'))